Zobrazeno 1 - 10
of 1 248
pro vyhledávání: '"Liu, Jianlin"'
Autor:
Jiang, Xi, Chen, Ying, Nie, Qiang, Liu, Yong, Liu, Jianlin, Gao, Bin-Bin, Liu, Jun, Wang, Chengjie, Zheng, Feng
Publikováno v:
Advances in Neural Information Processing Systems 35, ISBN: 9781713871088, (2022)
Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experimental setting of clean training data. Training with noisy data is an i
Externí odkaz:
http://arxiv.org/abs/2403.14233
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Although several papers have designed unified models for this task, they of
Externí odkaz:
http://arxiv.org/abs/2403.14213
Publikováno v:
International Journal of Clothing Science and Technology, 2024, Vol. 36, Issue 4, pp. 740-759.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/IJCST-06-2023-0094
Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces. So in this paper, we propose a multi-frame depth estimation framework wh
Externí odkaz:
http://arxiv.org/abs/2305.06036
We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our pipeline, which
Externí odkaz:
http://arxiv.org/abs/2304.07979
Autor:
Wu, Lixia, Liu, Jianlin, Lou, Junhong, Hu, Haoyuan, Zheng, Jianbin, Wen, Haomin, Song, Chao, He, Shu
Text-based delivery addresses, as the data foundation for logistics systems, contain abundant and crucial location information. How to effectively encode the delivery address is a core task to boost the performance of downstream tasks in the logistic
Externí odkaz:
http://arxiv.org/abs/2304.01559
Autor:
Huang, Dihe, Chen, Ying, Ding, Yikang, Liao, Jinli, Liu, Jianlin, Wu, Kai, Nie, Qiang, Liu, Yong, Wang, Chengjie, Li, Zhiheng
Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to the applicability of well-explored 2D detection techniques. However, existing methods obtain BEV features by simply collapsing voxel or point features along t
Externí odkaz:
http://arxiv.org/abs/2209.09464
3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate multiview feature
Externí odkaz:
http://arxiv.org/abs/2208.14738
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important. Conventional methods detect and match tentative local features across the whole images, with heuristic consistency checks to guarantee
Externí odkaz:
http://arxiv.org/abs/2202.09050
Publikováno v:
In Engineering Fracture Mechanics 22 August 2024 307